; it contains indexing information so that files can be read back from the log efficiently. In order to maintain large free areas on disk for fast writing, we divide the log into segments and use a segment cleaner to compress the live information from heavily fragmented segments. We present a series

, and from a letter-based language model. This allows fast writing of anything predicted by the recognizer while also providing seamless fallback to letter-by-letter spelling for words not in the recognizer’s predictions. In a formative user study, expert users wrote at 40 (corrected) words per minute

Abstract not found

to newer objects is often called the remembered set [Ung86]. At every store, the system must ensure that the updated location is added to the remembered set if the store creates a reference from an older to a newer object. This mechanism is usually referred to as a write barrier or store check. For some

in the system can store, cache, or control any block of data. Our approach uses this location independence, in combination with fast local area networks, to provide better performance and scalability than traditional file systems. Further, because any machine in the system can assume the responsibilities of a

, I/O nodes, and I/O request sizes. We also present performance results for MPI-IO on PVFS, both for a concurrent read/write workload and for the BTIO benchmark. We compare the I/O performance when using a Myrinet network versus a fast-ethernet network for I/O-related communication in PVFS. We

This paper describes Purifyru, a software testing and quality assurance Ool that detects memory leaks and access erors. Purify inserts additional checking instructions directly into the object code produced by existing compilers. These instructions check every memory read and write performed

such as tracing, source code scanning, and functional analysis of the Files-11 file system helped determine which features should be supported by the emulation. The Spiralog file system uses extensive write-back caching to gain performance over the write-through cache on the Files-11 file system. Applications

This paper introduces the FAWN—Fast Array of Wimpy Nodes—cluster architecture for providing fast, scalable, and power-efficient key-value storage. A FAWN links together a large number of tiny nodes built using embedded processors and small amounts (2–16GB) of flash memory into an ensemble capable

to improve I/O performance in distributed file systems: non-volatile file caches on client workstations to reduce write traffic to file servers, and write buffers for write-optimized file systems to reduce server disk accesses. Our results show that a megabyte of NVRAM on diskless clients reduces the amount